Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Llama conversion script: adjustments for Llama Guard #27910

Merged

Conversation

pcuenca
Copy link
Member

@pcuenca pcuenca commented Dec 8, 2023

What does this PR do?

Small adjustments to the Llama 2 conversion script so it works with the original Llama Guard weights.

Before submitting

  • This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
  • Did you read the contributor guideline,
    Pull Request section?
  • Was this discussed/approved via a Github issue or the forum? Please add a link
    to it if that's the case.
  • Did you make sure to update the documentation with your changes? Here are the
    documentation guidelines, and
    here are tips on formatting docstrings.
  • Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag
members/contributors who may be interested in your PR.

cc @ArthurZucker

@@ -91,6 +91,7 @@ def write_model(model_path, input_base_path, model_size, tokenizer_path=None, sa

params = read_json(os.path.join(input_base_path, "params.json"))
num_shards = NUM_SHARDS[model_size]
params = params.get("model", params)
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Reason: Model parameters are nested in the Llama Guard configuration file: https://huggingface.co/meta-llama/LlamaGuard-7b/blob/main/params.json#L67, whereas they weren't in previous releases.

Comment on lines -112 to +113
if "n_kv_heads" in params:
if params.get("n_kv_heads", None) is not None:
Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@pcuenca pcuenca requested a review from ArthurZucker December 8, 2023 14:20
Copy link
Collaborator

@ArthurZucker ArthurZucker left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for updating! 🔥

@ArthurZucker ArthurZucker merged commit e0b617d into huggingface:main Dec 8, 2023
8 checks passed
@pcuenca pcuenca deleted the support-llama-guard-conversion branch December 8, 2023 16:19
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants